Geographic tipping points in ecosystems, climate subsystems, or ice sheets pose severe challenges for localized early warning. Classical spatial indicators such as Moran's I summarize global spatial structure, but they struggle with three issues: spatial dilution, Euclidean assumptions, and correlated noise. This paper introduces SpatioTemporal Causal Network Diagnostics (ST-CND), a framework that addresses these three issues by representing the geographic field as a time-evolving directed causal network. The core workflow is: (1) infer which spatial nodes help predict other nodes via transfer entropy, replacing fixed Euclidean neighbourhoods with data-driven information-flow topology; (2) estimate local recovery rate within each candidate subnetwork via dynamic mode decomposition; (3) identify the most vulnerable subnetwork by combining three signals — high internal fluctuation, high internal synchronization, and low external coupling — which suppresses false alarms from spatially correlated noise. Validated on synthetic bifurcations and two observational sea-surface temperature benchmarks (Indo-Pacific SST and North Atlantic AMOC), ST-CND delivers localized, interpretable warnings. On the AMOC task, it achieves AUROC 0.783 and critical subnetwork IoU 0.378, outperforming recurrence-network and $\lambda$-AR1 baselines. The framework provides an interpretable and scalable pipeline for spatial early warning in Earth system science.

暂无